Metabolomic profiles predict individual multidisease outcomes

Метаболомные профили прогнозируют индивидуальные исходы при множественных заболеваниях
Thore Buergel, Jakob Steinfeldt, Greg Ruyoga, Maik Pietzner, Daniele Bizzarri, Dina Vojinović, Julius Upmeier zu Belzen, Lukas Loock, Paul Kittner, Lara Christmann, Noah Hollmann, Henrik Strangalies, Jana M. Braunger, Benjamin Wild, Scott T. Chiesa, Joachim Spranger, Fabian Klostermann, Erik B. van den Akker, Stella Trompet, Simon P. Mooijaart, Naveed A. Sattar, J. Wouter Jukema, Birgit D. A. Lavrijssen, Maryam Kavousi, Mohsen Ghanbari, M. Arfan Ikram, P. Eline Slagboom, Mika Kivimäki, Claudia Langenberg, John Eric Deanfield, Roland Eils, Ulf Landmesser
2022-09-22

NMR-derived metabolomicsUK Biobankmetabolic biomarkersmultidisease risk predictionneural network
Risk stratification is critical for the early identification of high-risk individuals and disease prevention. Here we explored the potential of nuclear magnetic resonance (NMR) spectroscopy-derived metabolomic profiles to inform on multidisease risk beyond conventional clinical predictors for the onset of 24 common conditions, including metabolic, vascular, respiratory, musculoskeletal and neurological diseases and cancers. Specifically, we trained a neural network to learn disease-specific metabolomic states from 168 circulating metabolic markers measured in 117,981 participants with ~1.4 million person-years of follow-up from the UK Biobank and validated the model in four independent cohorts. We found metabolomic states to be associated with incident event rates in all the investigated conditions, except breast cancer. For 10-year outcome prediction for 15 endpoints, with and without established metabolic contribution, a combination of age and sex and the metabolomic state equaled or outperformed established predictors. Moreover, metabolomic state added predictive information over comprehensive clinical variables for eight common diseases, including type 2 diabetes, dementia and heart failure. Decision curve analyses showed that predictive improvements translated into clinical utility for a wide range of potential decision thresholds. Taken together, our study demonstrates both the potential and limitations of NMR-derived metabolomic profiles as a multidisease assay to inform on the risk of many common diseases simultaneously.
1
A neural network learned disease-specific metabolomic states from 168 circulating markers in 117,981 UK Biobank participants with approximately 1.4 million person-years of follow-up.
2
Decision curve analyses indicated that metabolomic improvements translated into clinical utility across a wide range of decision thresholds, while also demonstrating assay limitations.
3
For 15 endpoints, age, sex, and metabolomic state matched or outperformed established predictors of 10-year outcomes.
4
Metabolomic state provided predictive information beyond comprehensive clinical variables for eight diseases, including type 2 diabetes, dementia, and heart failure.
5
Metabolomic states were associated with incident event rates for all 24 investigated conditions except breast cancer.

NMR spectroscopy-derived circulating metabolomic profiles in individuals

Multidisease risk prediction and incremental prognostic value beyond conventional clinical predictors

Publication Details
Publication Date
2022-09-22
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Thore Buergel
Jakob Steinfeldt
Greg Ruyoga
Maik Pietzner
Daniele Bizzarri
Dina Vojinović
Julius Upmeier zu Belzen
Lukas Loock
Paul Kittner
Lara Christmann
Noah Hollmann
Henrik Strangalies
Jana M. Braunger
Benjamin Wild
Scott T. Chiesa
Joachim Spranger
Fabian Klostermann
Erik B. van den Akker
Stella Trompet
Simon P. Mooijaart
Naveed A. Sattar
J. Wouter Jukema
Birgit D. A. Lavrijssen
Maryam Kavousi
Mohsen Ghanbari
M. Arfan Ikram
P. Eline Slagboom
Mika Kivimäki
Claudia Langenberg
John Eric Deanfield
Roland Eils
Ulf Landmesser
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%